A Novel Demand Response Model and Method for Peak Reduction in Smart Grids - PowerTAC
Abstract
We study the Demand Response behavior of smart grid customers in response to the offered discounts for peak reduction. We propose a model that depicts the probability of a customer reducing its load as a function of the discounts offered. This function is parametrized by the rate of reduction (RR). We provide an optimal algorithm, MJS-ExpResponse, that allocates the discounts to each customer by maximizing the expected reduction under a budget constraint. When RRs are unknown, we propose a Multi-Armed Bandit based online algorithm, namely MJSUCB-ExpResponse, to learn RRs. We experimentally show that it exhibits sublinear regret and showcase its efficacy in a real-world smart grid system using the PowerTAC simulator as a test bed.